library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(plotly)
## Loading required package: ggplot2
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(ggplot2)
Is there an association between the percentage of people who graduated high school and the incidence rate 1) across neighborhoods in NYC and 2) across neighborhoods in each borough?
data_clean <- read.csv("data_final.csv")
# List all column names
names(data_clean)
## [1] "INCIDENT_KEY" "OCCUR_DATE"
## [3] "OCCUR_TIME" "BORO"
## [5] "LOC_OF_OCCUR_DESC" "PRECINCT"
## [7] "JURISDICTION_CODE" "LOC_CLASSFCTN_DESC"
## [9] "LOCATION_DESC" "STATISTICAL_MURDER_FLAG"
## [11] "PERP_AGE_GROUP" "PERP_SEX"
## [13] "PERP_RACE" "VIC_AGE_GROUP"
## [15] "VIC_SEX" "VIC_RACE"
## [17] "X_COORD_CD" "Y_COORD_CD"
## [19] "Latitude" "Longitude"
## [21] "Lon_Lat" "Neighborhood"
## [23] "neighbourhood_group" "NTA"
## [25] "Is_Holiday" "Year"
## [27] "Month" "OCCUR_DATETIME"
## [29] "Sky_Is_Dark" "NTAType"
## [31] "Total_population_nta" "CDTA"
## [33] "Number_poverty" "Percent_poverty"
## [35] "Number_education" "Percent_education"
## [37] "incident_rate_by_year_nta" "total_population_boro"
## [39] "incident_rate_by_year_boro"
# Check the structure of the data frame
str(data_clean)
## 'data.frame': 9820 obs. of 39 variables:
## $ INCIDENT_KEY : int 244608249 247542571 202853370 230311078 229224142 231246224 228559720 238210279 233431365 238238212 ...
## $ OCCUR_DATE : chr "2022-05-05" "2022-07-04" "2019-09-24" "2021-07-01" ...
## $ OCCUR_TIME : chr "00:10:00" "22:20:00" "21:00:00" "23:07:00" ...
## $ BORO : chr "MANHATTAN" "BRONX" "BRONX" "MANHATTAN" ...
## $ LOC_OF_OCCUR_DESC : chr "INSIDE" "OUTSIDE" NA NA ...
## $ PRECINCT : int 14 48 42 23 113 77 48 49 73 114 ...
## $ JURISDICTION_CODE : int 0 0 0 2 0 0 0 0 0 0 ...
## $ LOC_CLASSFCTN_DESC : chr "COMMERCIAL" "STREET" NA NA ...
## $ LOCATION_DESC : chr "VIDEO STORE" "(null)" NA "MULTI DWELL - PUBLIC HOUS" ...
## $ STATISTICAL_MURDER_FLAG : logi TRUE TRUE FALSE FALSE TRUE FALSE ...
## $ PERP_AGE_GROUP : chr "25-44" "(null)" "25-44" NA ...
## $ PERP_SEX : chr "M" "(null)" "M" NA ...
## $ PERP_RACE : chr "BLACK" "(null)" "UNKNOWN" NA ...
## $ VIC_AGE_GROUP : chr "25-44" "18-24" "25-44" "25-44" ...
## $ VIC_SEX : chr "M" "M" "M" "M" ...
## $ VIC_RACE : chr "BLACK" "BLACK" "BLACK" "BLACK" ...
## $ X_COORD_CD : num 986050 1016802 1014493 999061 1042534 ...
## $ Y_COORD_CD : num 214231 250581 242565 229912 184647 ...
## $ Latitude : num 40.8 40.9 40.8 40.8 40.7 ...
## $ Longitude : num -74 -73.9 -73.9 -73.9 -73.8 ...
## $ Lon_Lat : chr "POINT (-73.9935 40.754692)" "POINT (-73.88233 40.854402)" "POINT (-73.89071440599997 40.832416753000075)" "POINT (-73.94650786199998 40.79772716600007)" ...
## $ Neighborhood : chr "Hell's Kitchen" "Belmont" "East Morrisania" "East Harlem" ...
## $ neighbourhood_group : chr "Manhattan" "Bronx" "Bronx" "Manhattan" ...
## $ NTA : chr "Chelsea-Hudson Yards" "Belmont" "Crotona Park East" "East Harlem (North)" ...
## $ Is_Holiday : logi FALSE TRUE FALSE FALSE FALSE FALSE ...
## $ Year : int 2022 2022 2019 2021 2021 2021 2021 2021 2021 2021 ...
## $ Month : int 5 7 9 7 6 7 5 12 9 12 ...
## $ OCCUR_DATETIME : chr "2022-05-05 00:10:00" "2022-07-04 22:20:00" "2019-09-24 21:00:00" "2021-07-01 23:07:00" ...
## $ Sky_Is_Dark : logi TRUE TRUE TRUE TRUE FALSE TRUE ...
## $ NTAType : chr "Residential" "Residential" "Residential" "Residential" ...
## $ Total_population_nta : int 69741 35825 30158 64655 43090 15 35825 34623 37952 50225 ...
## $ CDTA : chr "MN 04" "BX 06" "BX 03" "MN 11" ...
## $ Number_poverty : chr "7,121" "12,919" "8,519" "20,588" ...
## $ Percent_poverty : num 11.5 39.6 29.4 32.3 11.4 NA 39.6 24.6 27.3 9.4 ...
## $ Number_education : chr "49,919" "12,455" "13,149" "34,290" ...
## $ Percent_education : num 94.6 65.6 69 75.9 83.5 NA 65.6 75.7 83.1 88.4 ...
## $ incident_rate_by_year_nta : num 0.0272 0.0809 0.0365 0.0619 0.0278 ...
## $ total_population_boro : int 18415085 22955825 11660890 20085354 13629328 38087730 29778638 29778638 38087730 13629328 ...
## $ incident_rate_by_year_boro: num 0.00167 0.00233 0.00229 0.00171 0.00217 ...
# Step 1: Check the structure of your dataset to ensure the necessary columns exist
head(data_clean)
## INCIDENT_KEY OCCUR_DATE OCCUR_TIME BORO LOC_OF_OCCUR_DESC PRECINCT
## 1 244608249 2022-05-05 00:10:00 MANHATTAN INSIDE 14
## 2 247542571 2022-07-04 22:20:00 BRONX OUTSIDE 48
## 3 202853370 2019-09-24 21:00:00 BRONX <NA> 42
## 4 230311078 2021-07-01 23:07:00 MANHATTAN <NA> 23
## 5 229224142 2021-06-07 19:55:00 QUEENS <NA> 113
## 6 231246224 2021-07-22 01:47:00 BROOKLYN <NA> 77
## JURISDICTION_CODE LOC_CLASSFCTN_DESC LOCATION_DESC
## 1 0 COMMERCIAL VIDEO STORE
## 2 0 STREET (null)
## 3 0 <NA> <NA>
## 4 2 <NA> MULTI DWELL - PUBLIC HOUS
## 5 0 <NA> <NA>
## 6 0 <NA> MULTI DWELL - APT BUILD
## STATISTICAL_MURDER_FLAG PERP_AGE_GROUP PERP_SEX PERP_RACE VIC_AGE_GROUP
## 1 TRUE 25-44 M BLACK 25-44
## 2 TRUE (null) (null) (null) 18-24
## 3 FALSE 25-44 M UNKNOWN 25-44
## 4 FALSE <NA> <NA> <NA> 25-44
## 5 TRUE <NA> <NA> <NA> 45-64
## 6 FALSE <NA> <NA> <NA> 25-44
## VIC_SEX VIC_RACE X_COORD_CD Y_COORD_CD Latitude Longitude
## 1 M BLACK 986050 214231 40.75469 -73.99350
## 2 M BLACK 1016802 250581 40.85440 -73.88233
## 3 M BLACK 1014493 242565 40.83242 -73.89071
## 4 M BLACK 999061 229912 40.79773 -73.94651
## 5 M BLACK 1042534 184647 40.67331 -73.78989
## 6 M BLACK 1004507 182865 40.66858 -73.92698
## Lon_Lat Neighborhood
## 1 POINT (-73.9935 40.754692) Hell's Kitchen
## 2 POINT (-73.88233 40.854402) Belmont
## 3 POINT (-73.89071440599997 40.832416753000075) East Morrisania
## 4 POINT (-73.94650786199998 40.79772716600007) East Harlem
## 5 POINT (-73.78988688199998 40.673306465000046) Jamaica
## 6 POINT (-73.92697993199994 40.66858395700007) Crown Heights
## neighbourhood_group NTA Is_Holiday Year Month
## 1 Manhattan Chelsea-Hudson Yards FALSE 2022 5
## 2 Bronx Belmont TRUE 2022 7
## 3 Bronx Crotona Park East FALSE 2019 9
## 4 Manhattan East Harlem (North) FALSE 2021 7
## 5 Queens Baisley Park FALSE 2021 6
## 6 Brooklyn Lincoln Terrace Park FALSE 2021 7
## OCCUR_DATETIME Sky_Is_Dark NTAType Total_population_nta CDTA
## 1 2022-05-05 00:10:00 TRUE Residential 69741 MN 04
## 2 2022-07-04 22:20:00 TRUE Residential 35825 BX 06
## 3 2019-09-24 21:00:00 TRUE Residential 30158 BX 03
## 4 2021-07-01 23:07:00 TRUE Residential 64655 MN 11
## 5 2021-06-07 19:55:00 FALSE Residential 43090 QN 12
## 6 2021-07-22 01:47:00 TRUE Park 15 BK 08
## Number_poverty Percent_poverty Number_education Percent_education
## 1 7,121 11.5 49,919 94.6
## 2 12,919 39.6 12,455 65.6
## 3 8,519 29.4 13,149 69.0
## 4 20,588 32.3 34,290 75.9
## 5 5,054 11.4 25,416 83.5
## 6 <NA> NA <NA> NA
## incident_rate_by_year_nta total_population_boro incident_rate_by_year_boro
## 1 0.02724366 18415085 0.001667112
## 2 0.08094906 22955825 0.002330563
## 3 0.03647457 11660890 0.002289705
## 4 0.06186683 20085354 0.001707712
## 5 0.02784869 13629328 0.002171787
## 6 13.33333333 38087730 0.001656702
# Calculate the correlation between the poverty percentage and the incident rate
correlation <- cor(data_clean$incident_rate_by_year_nta, data_clean$Percent_education, use = "complete.obs")
print(paste("Correlation coefficient: ", correlation))
## [1] "Correlation coefficient: -0.274782643621429"
# Create a scatter plot to visualize the relationship
data_clean %>%
plot_ly(x = ~Percent_education, y = ~incident_rate_by_year_nta,
color = ~NTA, colors = "viridis",
type = "scatter", mode = "markers",
text = ~paste("Neighborhood: ", NTA, "<br>Borough: ", BORO,
"<br>% graduated HS: ", Percent_education,
"<br>Incident Rate: ", incident_rate_by_year_nta)) %>%
layout(title = "Percent graduated high school and Incident Rate in NYC",
xaxis = list(title = 'Percentage of People graduated in high school'),
yaxis = list(title = 'Incident Rate'),
legend = list(title = list(text = 'Neighborhood')))
## Warning: Ignoring 95 observations
# Assuming your main data frame is named 'data_clean'
# Filter data for Manhattan
manhattan_data <- data_clean %>%
filter(neighbourhood_group == "Manhattan")
# Filter data for Brooklyn
brooklyn_data <- data_clean %>%
filter(neighbourhood_group == "Brooklyn")
# Filter data for The Bronx
bronx_data <- data_clean %>%
filter(neighbourhood_group == "Bronx")
# Filter data for Staten Island
staten_island_data <- data_clean %>%
filter(neighbourhood_group == "Staten Island")
# Filter data for Queens
queens_data <- data_clean %>%
filter(neighbourhood_group == "Queens")
# Function to compute and print correlation
compute_correlation <- function(data, borough_name) {
correlation <- cor(
data$incident_rate_by_year_nta,
data$Percent_education,
use = "complete.obs"
)
cat("Correlation coefficient for", borough_name, ":", correlation, "\n")
}
compute_correlation(manhattan_data, "Manhattan")
## Correlation coefficient for Manhattan : -0.2284435
compute_correlation(brooklyn_data, "Brooklyn")
## Correlation coefficient for Brooklyn : -0.248732
compute_correlation(bronx_data, "Bronx")
## Correlation coefficient for Bronx : -0.3996457
compute_correlation(staten_island_data, "Staten Island")
## Correlation coefficient for Staten Island : -0.6452131
compute_correlation(queens_data, "Queens")
## Correlation coefficient for Queens : 0.1006569
compute_correlation(manhattan_data, "Manhattan")
## Correlation coefficient for Manhattan : -0.2284435
# Function to create scatter plot with trend line
# Scatter plot for Manhattan
data_clean |>
filter(neighbourhood_group == "Manhattan") |>
plot_ly(data = _, x = ~Percent_education, y = ~incident_rate_by_year_nta,
color = ~NTA,
colors = "viridis",
type = "scatter",
mode = "markers",
text = ~paste("Neighborhood: ", NTA, "<br>Borough: ", neighbourhood_group,
"<br>% graduated HS: ", Percent_education,
"<br>Incident Rate: ", incident_rate_by_year_nta)) |>
layout(title = "Percent graduated high school and Incident Rate in Manhattan",
xaxis = list(title = 'Percentage of People graduated in high school'),
yaxis = list(title = 'Incident Rate'),
legend = list(title = list(text = 'Neighborhood')))
## Warning: Ignoring 6 observations
# Scatter plot for Brooklyn
data_clean |>
filter(neighbourhood_group == "Brooklyn") |>
plot_ly(data = _, x = ~Percent_poverty, y = ~incident_rate_by_year_nta,
color = ~NTA,
colors = "plasma",
type = "scatter",
mode = "markers",
text = ~paste("Neighborhood: ", NTA, "<br>Borough: ", neighbourhood_group,
"<br>% graduated HS: ", Percent_education,
"<br>Incident Rate: ", incident_rate_by_year_nta)) |>
layout(title = "Percent graduated high school and Incident Rate in Brooklyn",
xaxis = list(title = 'Percentage of People graduated in high school'),
yaxis = list(title = 'Incident Rate'),
legend = list(title = list(text = 'Neighborhood')))
## Warning: Ignoring 13 observations
# Scatter plot for The Bronx
data_clean |>
filter(neighbourhood_group == "Bronx") |>
plot_ly(data = _, x = ~Percent_poverty, y = ~incident_rate_by_year_nta,
color = ~NTA,
colors = "magma",
type = "scatter",
mode = "markers",
text = ~paste("Neighborhood: ", NTA, "<br>Borough: ", neighbourhood_group,
"<br>% graduated HS: ", Percent_education,
"<br>Incident Rate: ", incident_rate_by_year_nta)) |>
layout(title = "Percent graduated high school and Incident Rate in The Bronx",
xaxis = list(title = 'Percentage of People graduated in high school'),
yaxis = list(title = 'Incident Rate'),
legend = list(title = list(text = 'Neighborhood')))
## Warning: Ignoring 25 observations
# Scatter plot for Queens
data_clean |>
filter(neighbourhood_group == "Queens") |>
plot_ly(data = _, x = ~Percent_poverty, y = ~incident_rate_by_year_nta,
color = ~NTA,
colors = "inferno",
type = "scatter",
mode = "markers",
text = ~paste("Neighborhood: ", NTA, "<br>Borough: ", neighbourhood_group,
"<br>% graduated HS: ", Percent_education,
"<br>Incident Rate: ", incident_rate_by_year_nta)) |>
layout(title = "Percent graduated high school and Incident Rate in Queens",
xaxis = list(title = 'Percentage of People graduated in high school'),
yaxis = list(title = 'Incident Rate'),
legend = list(title = list(text = 'Neighborhood')))
## Warning: Ignoring 11 observations
# Scatter plot for Staten Island
data_clean |>
filter(neighbourhood_group == "Staten Island") |>
plot_ly(data = _, x = ~Percent_poverty, y = ~incident_rate_by_year_nta,
color = ~NTA,
colors = "inferno",
type = "scatter",
mode = "markers",
text = ~paste("Neighborhood: ", NTA, "<br>Borough: ", neighbourhood_group,
"<br>% graduated HS: ", Percent_education,
"<br>Incident Rate: ", incident_rate_by_year_nta)) |>
layout(title = "Percent graduated high school and Incident Rate in Queens",
xaxis = list(title = 'Percentage of People graduated in Staten Island'),
yaxis = list(title = 'Incident Rate'),
legend = list(title = list(text = 'Neighborhood')))
## Warning: Ignoring 5 observations